Skip to content
  1. Home
  2. Agent skills
  3. Hyperresearch

Hyperresearch

Multi-step deep research pipeline for Claude Code and Codex

What it is

A research harness that runs a 16-step pipeline from a single prompt and produces a report with audited claims and source provenance. Every source it reads is stored in a persistent, searchable local vault so later sessions can reuse it. Installs as a skill with subagents and a hook that prevents skipped steps.

Good for

  • Write a sourced report on a technical topic
  • Build a reusable vault of read sources
  • Audit claims against their citations

Install or run

pip install hyperresearch

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Python; Claude Code or Codex with web access

Worth knowingLong runs use many tokens; the benchmark ranking quoted in the README is for the paid hosted version and was measured on only 10 tasks.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • arXiv Search

    NousResearch/hermes-agent

    Search arXiv papers by keyword, author, category or ID

    SkillGitHub stars: 263k
  • Blocked Page Recovery

    NousResearch/hermes-agent

    Recover content when a fetch hits 403, a paywall or a bot wall

    SkillGitHub stars: 263k
  • Grounded Citations

    NousResearch/hermes-agent

    Numbered inline citations backed by a URL ledger script

    SkillGitHub stars: 263k
  • xlsx

    anthropics/skills

    Create, edit and clean Excel and CSV spreadsheets

    SkillGitHub stars: 194k